In this notebook, a template is provided for you to implement your functionality in stages which is required to successfully complete this project. If additional code is required that cannot be included in the notebook, be sure that the Python code is successfully imported and included in your submission, if necessary. Sections that begin with 'Implementation' in the header indicate where you should begin your implementation for your project. Note that some sections of implementation are optional, and will be marked with 'Optional' in the header.
In addition to implementing code, there will be questions that you must answer which relate to the project and your implementation. Each section where you will answer a question is preceded by a 'Question' header. Carefully read each question and provide thorough answers in the following text boxes that begin with 'Answer:'. Your project submission will be evaluated based on your answers to each of the questions and the implementation you provide.
Note: Code and Markdown cells can be executed using the Shift + Enter keyboard shortcut. In addition, Markdown cells can be edited by typically double-clicking the cell to enter edit mode.
# Load pickled data
import pickle
# TODO: Fill this in based on where you saved the training and testing data
training_file = "./traffic-signs-data/train.p"
testing_file = "./traffic-signs-data/test.p"
with open(training_file, mode='rb') as f:
train = pickle.load(f)
with open(testing_file, mode='rb') as f:
test = pickle.load(f)
X_train, y_train = train['features'], train['labels']
X_test, y_test = test['features'], test['labels']
The pickled data is a dictionary with 4 key/value pairs:
'features' is a 4D array containing raw pixel data of the traffic sign images, (num examples, width, height, channels).'labels' is a 1D array containing the label/class id of the traffic sign. The file signnames.csv contains id -> name mappings for each id.'sizes' is a list containing tuples, (width, height) representing the the original width and height the image.'coords' is a list containing tuples, (x1, y1, x2, y2) representing coordinates of a bounding box around the sign in the image. THESE COORDINATES ASSUME THE ORIGINAL IMAGE. THE PICKLED DATA CONTAINS RESIZED VERSIONS (32 by 32) OF THESE IMAGESComplete the basic data summary below.
### Replace each question mark with the appropriate value.
# TODO: Number of training examples
n_train = len(train['labels'])
# TODO: Number of testing examples.
n_test = len(test['labels'])
# TODO: What's the shape of an traffic sign image?
image_shape = test['features'][0].shape
# TODO: How many unique classes/labels there are in the dataset.
import numpy as np
n_classes = len(np.unique(train['labels']))
print("Number of training examples =", n_train)
print("Number of testing examples =", n_test)
print("Image data shape =", image_shape)
print("Number of classes =", n_classes)
Visualize the German Traffic Signs Dataset using the pickled file(s). This is open ended, suggestions include: plotting traffic sign images, plotting the count of each sign, etc.
The Matplotlib examples and gallery pages are a great resource for doing visualizations in Python.
NOTE: It's recommended you start with something simple first. If you wish to do more, come back to it after you've completed the rest of the sections.
### Data exploration visualization goes here.
### Feel free to use as many code cells as needed.
# Visualizations will be shown in the notebook.
import random
import matplotlib.pyplot as plt
import csv
%matplotlib inline
import matplotlib.gridspec as gridspec
#import matplotlib as mpl
#mpl.rcParams.update(mpl.rcParamsDefault)
signnames={}
with open('signnames.csv', mode='r') as infile:
reader = csv.reader(infile)
signnames = {rows[0]:rows[1] for rows in reader}
signnames.pop('ClassId')
def showSample():
for num in range(n_classes):
plt.figure(num)
fig, axes = plt.subplots(1,10, figsize=(10,2),subplot_kw={'xticks': [], 'yticks': []})
plt.suptitle(signnames[str(num)], fontsize=14, fontweight='bold')
index = np.where(y_train==num)
index = np.array(index).flatten()
index = np.random.choice(index,10,replace=False)
a=0
for ax in axes.flat:
image = X_train[index[a]].squeeze()
ax.imshow(image)
a+=1
showSample()
Design and implement a deep learning model that learns to recognize traffic signs. Train and test your model on the German Traffic Sign Dataset.
There are various aspects to consider when thinking about this problem:
Here is an example of a published baseline model on this problem. It's not required to be familiar with the approach used in the paper but, it's good practice to try to read papers like these.
NOTE: The LeNet-5 implementation shown in the classroom at the end of the CNN lesson is a solid starting point. You'll have to change the number of classes and possibly the preprocessing, but aside from that it's plug and play!
Use the code cell (or multiple code cells, if necessary) to implement the first step of your project. Once you have completed your implementation and are satisfied with the results, be sure to thoroughly answer the questions that follow.
### Preprocess the data here.
### Feel free to use as many code cells as needed.
def preprocessing(X):
X /= np.std(X, axis = 0)
return X
X_train = preprocessing(X_train.astype('f'))
X_test = preprocessing(X_test.astype('f'))
showSample()
Describe how you preprocessed the data. Why did you choose that technique?
Answer: Since each image has different contrast variations, I attempted to center the image(Mean subtract) and nomalize the values to make them have same scale. So I tried 4 mothods combining with combining each methods. After that, I figured out that just nomalize with dividing by standard deviation makes good results as below. (Method : Accuracy for test data)
### Generate additional data (OPTIONAL!)
### and split the data into training/validation/testing sets here.
### Feel free to use as many code cells as needed.
from sklearn.utils import shuffle
from sklearn.model_selection import train_test_split
X_train, y_train = shuffle(X_train, y_train)
X_train, X_validation, y_train, y_validation = train_test_split(X_train, y_train, test_size=0.15)
Describe how you set up the training, validation and testing data for your model. Optional: If you generated additional data, how did you generate the data? Why did you generate the data? What are the differences in the new dataset (with generated data) from the original dataset?
Answer:
### Define your architecture here.
### Feel free to use as many code cells as needed.
### Weight Initializer
import math
def xavier_init(n_inputs, n_outputs, uniform=True):
"""Set the parameter initialization using the method described.
This method is designed to keep the scale of the gradients roughly the same
in all layers.
Xavier Glorot and Yoshua Bengio (2010):
Understanding the difficulty of training deep feedforward neural
networks. International conference on artificial intelligence and
statistics.
Args:
n_inputs: The number of input nodes into each output.
n_outputs: The number of output nodes for each input.
uniform: If true use a uniform distribution, otherwise use a normal.
Returns:
An initializer.
"""
if uniform:
# 6 was used in the paper.
init_range = math.sqrt(6.0 / (n_inputs + n_outputs))
return tf.random_uniform_initializer(-init_range, init_range)
else:
# 3 gives us approximately the same limits as above since this repicks
# values greater than 2 standard deviations from the mean.
stddev = math.sqrt(3.0 / (n_inputs + n_outputs))
return tf.truncated_normal_initializer(stddev=stddev)
import tensorflow as tf
from tensorflow.contrib.layers import flatten
def model(x):
# Arguments used for tf.truncated_normal, randomly defines variables for the weights and biases for each layer
mu = 0
sigma = 0.1
# Convolutional. Input = 32x32x3. Output = 30x30x64.
conv1_W = tf.Variable(tf.truncated_normal(shape=(3, 3, 3, 64), mean = mu, stddev = sigma))
conv1_b = tf.Variable(tf.zeros(64))
conv1 = tf.nn.conv2d(x, conv1_W, strides=[1, 1, 1, 1], padding='VALID') + conv1_b
# Relu Activation
conv1 = tf.nn.relu(conv1)
# Max Pooling. Input = 30x30x64. Output = 15x15x64.
conv1 = tf.nn.max_pool(conv1, ksize=[1, 2, 2, 1], strides=[1, 2, 2, 1], padding='VALID')
# Convolutional. Input = 15x15x64. Output = 12x12x128.
conv2_W = tf.Variable(tf.truncated_normal(shape=(4, 4, 64, 128), mean = mu, stddev = sigma))
conv2_b = tf.Variable(tf.zeros(128))
conv2 = tf.nn.conv2d(conv1, conv2_W, strides=[1, 1, 1, 1], padding='VALID') + conv2_b
# Relu Activation.
conv2 = tf.nn.relu(conv2)
# Max Pooling. Input = 12x12x128. Output = 6x6x128.
conv2 = tf.nn.max_pool(conv2, ksize=[1, 2, 2, 1], strides=[1, 2, 2, 1], padding='VALID')
# Flatten. Input = 6x6x128. Output = 4608.
fc0 = flatten(conv2)
# Fully Connected. Input = 4608. Output = 120.
fc1_W = tf.get_variable("fc1_W", shape=[4608, 120], initializer = xavier_init(4608, 120))
fc1_b = tf.Variable(tf.zeros(120))
fc1 = tf.matmul(fc0, fc1_W) + fc1_b
# Relu Activation.
fc1 = tf.nn.relu(fc1)
# Fully Connected. Input = 120. Output = 84.
fc2_W = tf.get_variable("fc2_W", shape=[120, 84], initializer = xavier_init(120, 84))
fc2_b = tf.Variable(tf.zeros(84))
fc2 = tf.matmul(fc1, fc2_W) + fc2_b
# Relu Activation.
fc2 = tf.nn.relu(fc2)
# Fully Connected. Input = 84. Output = 43.
fc3_W = tf.get_variable("fc3_W", shape=[84, 43], initializer = xavier_init(84, 43))
fc3_b = tf.Variable(tf.zeros(43))
logits = tf.matmul(fc2, fc3_W) + fc3_b
return logits
What does your final architecture look like? (Type of model, layers, sizes, connectivity, etc.) For reference on how to build a deep neural network using TensorFlow, see Deep Neural Network in TensorFlow from the classroom.
Answer:
I use Xavier's algorithm to optimize initial weight values.
### Train your model here.
### Feel free to use as many code cells as needed.
EPOCHS = 20
BATCH_SIZE = 128
rate = 0.001
x = tf.placeholder(tf.float32, (None, 32, 32, 3))
y = tf.placeholder(tf.int32, (None))
one_hot_y = tf.one_hot(y, 43)
logits = model(x)
cross_entropy = tf.nn.softmax_cross_entropy_with_logits(logits, one_hot_y)
loss_operation = tf.reduce_mean(cross_entropy)
# Adam optimizer.
training_operation = tf.train.AdamOptimizer(learning_rate = rate).minimize(loss_operation)
correct_prediction = tf.equal(tf.argmax(logits, 1), tf.argmax(one_hot_y, 1))
accuracy_operation = tf.reduce_mean(tf.cast(correct_prediction, tf.float32))
saver = tf.train.Saver()
def evaluate(X_data, y_data):
num_examples = len(X_data)
total_accuracy = 0
sess = tf.get_default_session()
for offset in range(0, num_examples, BATCH_SIZE):
batch_x, batch_y = X_data[offset:offset+BATCH_SIZE], y_data[offset:offset+BATCH_SIZE]
accuracy = sess.run(accuracy_operation, feed_dict={x: batch_x, y: batch_y})
total_accuracy += (accuracy * len(batch_x))
return total_accuracy / num_examples
with tf.Session() as sess:
sess.run(tf.initialize_all_variables())
num_examples = len(X_train)
print("Training...")
print()
for i in range(EPOCHS):
X_train, y_train = shuffle(X_train, y_train)
for offset in range(0, num_examples, BATCH_SIZE):
end = offset + BATCH_SIZE
batch_x, batch_y = X_train[offset:end], y_train[offset:end]
sess.run(training_operation, feed_dict={x: batch_x, y: batch_y})
validation_accuracy = evaluate(X_validation, y_validation)
print("EPOCH {} ...".format(i+1))
print("Validation Accuracy = {:.3f}".format(validation_accuracy))
print()
saver.save(sess, './lenet')
print("Model saved")
with tf.Session() as sess:
saver.restore(sess, tf.train.latest_checkpoint('.'))
test_accuracy = evaluate(X_test, y_test)
print("Test Accuracy = {:.3f}".format(test_accuracy))
How did you train your model? (Type of optimizer, batch size, epochs, hyperparameters, etc.)
Answer:
What approach did you take in coming up with a solution to this problem? It may have been a process of trial and error, in which case, outline the steps you took to get to the final solution and why you chose those steps. Perhaps your solution involved an already well known implementation or architecture. In this case, discuss why you think this is suitable for the current problem.
Answer:
Step 1. Test with Lenet model -> Bad
Step 2. Apply Xavier's algorithm to optimize initial weight values. -> Good
Step 3. Apply Drop out(0.7) to 2 convolutional layers. -> Very Bad
Step 4. Add more convolutional layers with more channels, and smaller filter -> Very Good
Step 5. Increase number of epoch -> Good
Step 6. Preprocessing with several methods(Q1) -> Good
Order of Importance
Take several pictures of traffic signs that you find on the web or around you (at least five), and run them through your classifier on your computer to produce example results. The classifier might not recognize some local signs but it could prove interesting nonetheless.
You may find signnames.csv useful as it contains mappings from the class id (integer) to the actual sign name.
Use the code cell (or multiple code cells, if necessary) to implement the first step of your project. Once you have completed your implementation and are satisfied with the results, be sure to thoroughly answer the questions that follow.
### Load the images and plot them here.
### Feel free to use as many code cells as needed.
import matplotlib.pyplot as plt
from PIL import Image
import matplotlib.image as mpimg
imgLoc = ["./testimg/0.png"
,"./testimg/8.png"
,"./testimg/13.png"
,"./testimg/14.png"
,"./testimg/22.png"]
imgTitle=[]
X_img = []
y_imgTest = np.array([0,8,13,14,22])
fig, axes = plt.subplots(1,5, figsize=(10,10),subplot_kw={'xticks': [], 'yticks': []})
plt.subplots_adjust(left=0, bottom=0, right=1, top=1, wspace=2, hspace=0)
for ax, num in zip(axes.flat, range(5)):
X_img.append(np.array(Image.open(imgLoc[num]).resize((32,32),Image.ANTIALIAS)))
imgTitle.append(signnames[str(y_imgTest[num])])
ax.imshow(X_img[num])
ax.set_title(imgTitle[num])
X_imgTest = preprocessing(X_img)
Choose five candidate images of traffic signs and provide them in the report. Are there any particular qualities of the image(s) that might make classification difficult? It could be helpful to plot the images in the notebook.
Answer:
My model is trained by German traffic signs, so when I tried to test with another country's signs, the accuracy was decreased. So I refered to train images, and looked for similar designs(color, text, shape).
### Run the predictions here.
### Feel free to use as many code cells as needed.
with tf.Session() as sess:
saver.restore(sess, tf.train.latest_checkpoint('.'))
test_accuracy = evaluate(X_imgTest, y_imgTest)
print("Test Accuracy = {:.3f}".format(test_accuracy))
Is your model able to perform equally well on captured pictures when compared to testing on the dataset? The simplest way to do this check the accuracy of the predictions. For example, if the model predicted 1 out of 5 signs correctly, it's 20% accurate.
NOTE: You could check the accuracy manually by using signnames.csv (same directory). This file has a mapping from the class id (0-42) to the corresponding sign name. So, you could take the class id the model outputs, lookup the name in signnames.csv and see if it matches the sign from the image.
Answer:
Accracy on my 5 newly captured images is 100%, compare to 94% on my test set, and 99% on the validation set. So it seems like that my caputured images are similar with train set, and my model is overfitting.
### Visualize the softmax probabilities here.
### Feel free to use as many code cells as needed.
with tf.Session() as sess:
saver.restore(sess, tf.train.latest_checkpoint('.'))
predict = tf.nn.softmax(logits)
predict = tf.nn.top_k(predict,k=5)
sess = tf.get_default_session()
prediction = sess.run(predict, feed_dict={x:X_imgTest,y:y_imgTest})
print(prediction)
for num, (pos, values) in enumerate(zip(prediction.indices, prediction.values)):
ylabels=[]
for a in pos:
ylabels.append(signnames[str(a)])
plt.figure(figsize=(6,1))
gs = gridspec.GridSpec(1, 2, width_ratios=[1, 5])
plt.subplot(gs[0])
plt.imshow(X_img[num])
plt.axis('off')
plt.subplot(gs[1])
plt.barh(np.arange(5)+.5,values,align='center')
plt.xticks(np.arange(0.0,1.1,0.1),np.arange(0.0,1.1,0.1))
plt.yticks(np.arange(5)+.5, ylabels)
plt.gca().invert_yaxis()
plt.gca().yaxis.tick_right()
plt.gca().yaxis.set_label_position("right")
Use the model's softmax probabilities to visualize the certainty of its predictions, tf.nn.top_k could prove helpful here. Which predictions is the model certain of? Uncertain? If the model was incorrect in its initial prediction, does the correct prediction appear in the top k? (k should be 5 at most)
tf.nn.top_k will return the values and indices (class ids) of the top k predictions. So if k=3, for each sign, it'll return the 3 largest probabilities (out of a possible 43) and the correspoding class ids.
Take this numpy array as an example:
# (5, 6) array
a = np.array([[ 0.24879643, 0.07032244, 0.12641572, 0.34763842, 0.07893497,
0.12789202],
[ 0.28086119, 0.27569815, 0.08594638, 0.0178669 , 0.18063401,
0.15899337],
[ 0.26076848, 0.23664738, 0.08020603, 0.07001922, 0.1134371 ,
0.23892179],
[ 0.11943333, 0.29198961, 0.02605103, 0.26234032, 0.1351348 ,
0.16505091],
[ 0.09561176, 0.34396535, 0.0643941 , 0.16240774, 0.24206137,
0.09155967]])
Running it through sess.run(tf.nn.top_k(tf.constant(a), k=3)) produces:
TopKV2(values=array([[ 0.34763842, 0.24879643, 0.12789202],
[ 0.28086119, 0.27569815, 0.18063401],
[ 0.26076848, 0.23892179, 0.23664738],
[ 0.29198961, 0.26234032, 0.16505091],
[ 0.34396535, 0.24206137, 0.16240774]]), indices=array([[3, 0, 5],
[0, 1, 4],
[0, 5, 1],
[1, 3, 5],
[1, 4, 3]], dtype=int32))
Looking just at the first row we get [ 0.34763842, 0.24879643, 0.12789202], you can confirm these are the 3 largest probabilities in a. You'll also notice [3, 0, 5] are the corresponding indices.
Answer:
All my test images show their certainty almost 100% according to visualized softmax probabilities.
Note: Once you have completed all of the code implementations and successfully answered each question above, you may finalize your work by exporting the iPython Notebook as an HTML document. You can do this by using the menu above and navigating to \n", "File -> Download as -> HTML (.html). Include the finished document along with this notebook as your submission.